Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method for recommending actors based on entries in a particular database, the method comprising: accessing an irrelevant actors database to determine whether the irrelevant actors database includes a promising actor, wherein the irrelevant actors database comprises a first plurality of entries, and wherein each entry of the first plurality of entries comprises an actor identifier field and an actor score field; retrieving a first threshold value, wherein the first threshold value corresponds to a minimum actor score required for including an actor in a promising actors database, wherein the promising actors database comprises a second plurality of entries, and wherein each entry of the second plurality of entries comprises the actor identifier field and the actor score field; retrieving a second threshold value, wherein the second threshold value corresponds to a minimum actor score required for including an actor in a relevant actors database; searching, at a first frequency, the irrelevant actors database for an actor associated with a first entry having a value corresponding to the actor score field that is between the first threshold value and the second threshold value; retrieving, based on the searching, the first entry; updating the promising actors database by including the first entry in the promising actors database; updating the irrelevant actors database by deleting the first entry from the irrelevant actors database; updating the actor score field corresponding to the second plurality of entries based on a pre-defined factor; searching, at a second frequency, the promising actors database to determine whether the promising actors database includes a relevant actor, wherein the second frequency is greater than the first frequency; retrieving the second threshold value; determining whether the value corresponding to the actor score field associated with the first entry exceeds the second threshold value; in response to determining that the value corresponding to the actor score field associated with the first entry exceeds the second threshold value, updating the relevant actors database to include the first entry; and in response to receiving a request for an actor recommendation, providing the actor recommendation based on entries in the relevant actors database.
This invention relates to actor recommendation systems and addresses the problem of efficiently identifying and recommending relevant actors from a large pool of potential candidates. The method involves managing multiple databases of actors, including an "irrelevant actors database" and a "promising actors database." Each actor entry in these databases contains an actor identifier and an actor score. The system uses two threshold values: a first threshold for inclusion in the promising actors database and a second, higher threshold for inclusion in a "relevant actors database." The process begins by periodically searching the irrelevant actors database for actors whose scores fall between the first and second thresholds. When such an actor is found, their entry is moved from the irrelevant actors database to the promising actors database. The actor scores in the promising actors database are then updated based on a predefined factor. Subsequently, the promising actors database is searched more frequently for actors whose scores exceed the second threshold. If an actor's score surpasses this second threshold, they are moved to the relevant actors database. Finally, when a recommendation request is received, the system provides actor recommendations based on the entries currently in the relevant actors database.
2. The method of claim 1 , further comprising: searching, at the first frequency, the irrelevant actors database for a second actor associated with a second entry having a value corresponding to the actor score field exceeds the second threshold value; retrieving, based on the searching for the second actor associated with a second entry, the second entry; updating the relevant actors database by including the second entry in the relevant actors database; and updating the irrelevant actors database by deleting the second entry from the irrelevant actors database.
This invention relates to a system for dynamically managing databases of relevant and irrelevant actors in a networked environment, such as social media or recommendation systems. The problem addressed is the need to efficiently identify and transition actors (e.g., users, entities, or content) between relevance categories based on their engagement or interaction metrics. The method involves maintaining two databases: a relevant actors database and an irrelevant actors database. Each entry in these databases includes an actor score field representing a metric of relevance, such as engagement level, interaction frequency, or user feedback. The system periodically searches the irrelevant actors database at a first frequency to identify actors whose actor score exceeds a second threshold value. When such an actor is found, the corresponding entry is retrieved, added to the relevant actors database, and removed from the irrelevant actors database. This ensures that actors who become relevant over time are dynamically promoted to the relevant database, improving the accuracy of recommendations or filtering processes. The method also includes a complementary process where actors in the relevant actors database are periodically checked at a second frequency to determine if their actor score falls below a first threshold, triggering their demotion to the irrelevant database. This bidirectional updating mechanism ensures both databases remain current, optimizing system performance and relevance. The thresholds and frequencies can be adjusted based on system requirements or user behavior patterns.
3. The method of claim 1 , further comprising: searching, at a third frequency, the relevant actors database for a third actor associated with a third entry having a value corresponding to the actor score field that is less than the second threshold value; retrieving, based on the searching for the third actor associated with a third entry, the third entry; determining whether the value corresponding to the actor score field of the third entry is less than the first threshold value; in response to determining that the value corresponding to the actor score field of the third entry is less than the first threshold value, updating the irrelevant actors database by including the third entry in the irrelevant actors database; in response to determining that the value corresponding to the actor score field of the third entry is not less than the first threshold value, updating the promising actors database by including the third entry in the promising actors database; and updating the relevant actors database by deleting the third entry from the relevant actors database.
This invention relates to a system for managing and categorizing actors (e.g., individuals, entities, or accounts) based on their relevance to a given context, such as fraud detection, risk assessment, or user engagement. The system maintains three databases: a relevant actors database, a promising actors database, and an irrelevant actors database. Each actor entry in these databases includes an actor score field representing a relevance metric. The method involves searching the relevant actors database at a third frequency for a third actor with an entry whose actor score is below a second threshold value. If found, the entry is retrieved, and its actor score is compared to a first threshold value. If the score is below the first threshold, the entry is moved to the irrelevant actors database. If the score is not below the first threshold, the entry is moved to the promising actors database. In both cases, the entry is removed from the relevant actors database. This process ensures that actors are dynamically reassessed and categorized based on their evolving relevance scores, improving the accuracy of actor classification over time. The system helps filter out low-relevance actors while retaining or promoting those with higher relevance, optimizing resource allocation and decision-making.
4. The method of claim 1 , wherein the pre-defined factor based on which the actor score field associated with a given entry of the second plurality of entries is updated includes any of: a score assigned to a given actor, corresponding to the given entry, by a review source; number of media assets that the given actor has acted in; popularity of a media asset in which the given actor has acted; level of acting of the given actor; popularity of the given actor; salary of the given actor; and number of pre-defined awards that the given actor has received.
This invention relates to a system for evaluating actors in media assets, such as movies or TV shows, by analyzing various factors to determine their influence or importance. The system addresses the challenge of objectively assessing an actor's significance in a media asset by considering multiple data points rather than relying on subjective opinions or limited metrics. The method involves maintaining a database of entries, each associated with an actor and a media asset. Each entry includes an actor score field that is updated based on predefined factors. These factors include a score assigned by a review source, the number of media assets the actor has appeared in, the popularity of the media assets they have acted in, their acting skill level, their overall popularity, their salary, and the number of awards they have received. By aggregating these factors, the system generates a comprehensive actor score that reflects the actor's influence or importance in the media industry. This score can be used for recommendations, rankings, or other analytical purposes. The system dynamically updates the actor score as new data becomes available, ensuring the evaluation remains current.
5. The method of claim 1 , wherein updating the actor score field corresponding to a given entry of the second plurality of entries based on the pre-defined factor further comprises: retrieving a first actor score assigned to a given actor, corresponding to the given entry, by a first review source; retrieving a first importance level associated with the first review source, wherein the first importance level is an indicator of how important inclusion of the first actor score is in the computation of a new actor score corresponding to the given actor; retrieving a second score assigned to the given actor by a second review source; retrieving a second importance level associated with the second review source, wherein the second importance level is an indicator of how important inclusion of the second actor score is in the computation of the new actor score corresponding to the given actor and wherein the second importance level is less than the first importance level; computing the new actor score, wherein the new actor score is a weighted average of the first actor score and the second actor score and wherein the first actor score is weighted greater than the second actor score; and updating value of the actor score field corresponding to the given entry to the new actor score.
This invention relates to a system for computing and updating actor scores based on multiple review sources, where each source has an associated importance level. The problem addressed is the need to accurately assess an actor's performance or reputation by aggregating scores from different sources while accounting for the varying reliability or significance of those sources. The method involves retrieving a first actor score assigned by a first review source and its associated importance level, which indicates how influential that score should be in the final computation. A second actor score from a second review source is also retrieved, along with its importance level, which is lower than the first. The new actor score is then computed as a weighted average of the two scores, where the first score is weighted more heavily due to its higher importance level. The updated score is stored in the corresponding entry of a database. This approach ensures that more reliable or authoritative review sources have a greater impact on the final actor score, improving the accuracy and relevance of the assessment. The system dynamically adjusts the influence of each source based on predefined importance levels, allowing for flexible and adaptive scoring.
6. The method of claim 5 , wherein the first importance level is based on any of: popularity of the first review source; accuracy of the first review source; entity providing the first review source; and a user preference.
This invention relates to systems for evaluating and prioritizing review sources, particularly in contexts where multiple sources provide conflicting or varying reviews of a product, service, or entity. The problem addressed is the difficulty in determining which review sources are more reliable or relevant, especially when users or systems need to aggregate or filter reviews based on trustworthiness or user preferences. The method involves assigning an importance level to a first review source based on multiple factors. These factors include the popularity of the review source, which may indicate broader acceptance or credibility; the accuracy of the review source, which could be determined through historical verification or consistency with other sources; the entity providing the review source, which may influence trustworthiness based on reputation or affiliation; and user preferences, allowing customization based on individual or group priorities. The importance level is then used to weight or prioritize the review source in subsequent analysis, display, or decision-making processes. This approach helps users or automated systems identify the most relevant or trustworthy reviews, improving the reliability of aggregated feedback. The method may be applied in e-commerce, social media, or any domain where review aggregation is needed.
7. The method of claim 1 , wherein providing the actor recommendation based on entries in the relevant actors database further comprises: determining a user associated with the request for the actor recommendation; accessing a media consumption history data structure, associated with the user, to determine a first actor that the user prefers; determining a prominent role associated with the first actor, wherein the prominent role associated with the first actor is most common role of the first actor; determining a plurality of actors, included in the relevant actors database, wherein prominent role associated with each actor of the plurality of actors matches the prominent role of the first actor; and recommending a second actor of the plurality of actors.
This invention relates to a system for recommending actors based on a user's media consumption history. The problem addressed is the lack of personalized actor recommendations in media platforms, leading to generic or irrelevant suggestions. The solution involves analyzing a user's viewing history to identify preferred actors and their most common roles, then recommending other actors who have played similar prominent roles. The method begins by identifying the user making the recommendation request. It then accesses the user's media consumption history to determine a first actor the user frequently engages with. The system analyzes this actor's roles to identify their most common or prominent role. Using this role, the system searches a database of relevant actors to find others who have played similar prominent roles. From this filtered list, a second actor is recommended to the user. This approach ensures recommendations are tailored to the user's preferences by leveraging their viewing history and role-based similarities between actors. The system avoids generic suggestions by focusing on specific role matches rather than broad actor popularity. This method enhances user engagement by providing more relevant and personalized actor recommendations.
8. The method of claim 7 , wherein recommending the second actor of the plurality of actors further comprises: determining a prominent genre associated with the first actor, wherein the prominent genre associated with the first actor is most common genre associated with the first actor; determining an actor of the plurality of actors, wherein prominent genre associated with the actor of the plurality of actors matches the prominent genre associated with the first actor; and selecting the actor of the plurality of actors as the second actor.
This invention relates to a method for recommending actors in a collaborative creative project, such as film or television production, by analyzing genre associations. The problem addressed is the challenge of identifying suitable actors for a project based on their past work, particularly when matching them with a primary actor to ensure thematic or stylistic consistency. The method involves determining a prominent genre associated with a first actor, which is the most common genre in which that actor has previously worked. The system then identifies other actors whose prominent genre matches that of the first actor. From these candidates, an actor is selected as a second actor for the project. This ensures that the recommended actor has a similar genre background, which may improve compatibility in terms of acting style, audience expectations, or thematic alignment. The approach leverages genre data to enhance actor recommendations, potentially improving casting decisions by aligning actors with shared genre expertise. This can be particularly useful in automated casting systems or collaborative platforms where genre consistency is a key factor. The method may be part of a broader system for actor selection, where initial candidate pools are refined based on genre matching.
9. The method of claim 7 , wherein recommending the second actor of the plurality of actors further comprises: determining a prominent media asset industry associated with the first actor, wherein the prominent media asset industry associated with the first actor is most common media asset industry associated with the first actor; determining an actor of the plurality of actors, wherein prominent media asset industry associated with the actor of the plurality of actors matches the prominent media asset industry associated with the first actor; and selecting the actor of the plurality of actors as the second actor.
This invention relates to a method for recommending actors in the media industry, particularly for identifying suitable collaborators based on industry prominence. The method addresses the challenge of efficiently matching actors with similar industry backgrounds to enhance collaboration opportunities. The process involves analyzing a first actor's media asset history to determine their most common industry association, such as film, television, or theater. The system then identifies other actors whose primary industry association matches that of the first actor. These matching actors are ranked or selected as potential collaborators, ensuring alignment in industry experience. The method may also involve filtering or prioritizing actors based on additional criteria, such as past collaborations or performance metrics. By focusing on industry prominence, the system improves the relevance of actor recommendations, facilitating better casting decisions and partnerships in media production. The approach leverages data-driven analysis to streamline the selection process, reducing manual effort and improving accuracy in identifying compatible actors for projects.
10. The method of claim 7 , wherein determining the prominent role associated with the first actor comprises: determining a first media asset in which the first actor appears; retrieving a first credit list associated with the first media asset, wherein the first credit lists all actors appearing in the first media asset; determining a first position of the first actor in the first credit list and a total number of actors in the first credit list; computing a first rank percentage of the first actor based on the first position of the first actor in the first credit list and the total number of actors in the first credit list; determining a second media asset in which the first actor appears; retrieving a second credit list associated with the second media asset, wherein the second credit lists all actors appearing in the second media asset; determining a second position of the first actor in the second credit list and a total number of actors in the second credit list; computing a second rank percentage of the first actor based on the second position of the first actor in the second credit list and the total number of actors in the second credit list; computing, based on the first rank percentage and the second rank percentage, an average rank percentage of the first actor; retrieving a role probability distribution wherein the role probability distribution provides probabilities of various roles in media assets; determining a first role associated with the role probability distribution that has a cumulative probability range that includes the average rank percentage of the first actor; and selecting the first role as the prominent role.
This invention relates to determining the prominence of an actor in media assets by analyzing their position in credit lists. The problem addressed is the lack of an automated method to assess an actor's importance across multiple media assets based on their billing order in credits. The method involves identifying a first media asset featuring the actor and retrieving its credit list, which includes all actors in the asset. The actor's position in this list and the total number of actors are used to compute a rank percentage. This process is repeated for a second media asset featuring the same actor. The rank percentages from both assets are averaged to produce an overall rank percentage for the actor. A role probability distribution is then retrieved, which maps rank percentages to probable roles (e.g., lead, supporting, minor). The actor's average rank percentage is compared to this distribution to determine the role whose cumulative probability range includes the actor's rank. This role is selected as the actor's prominent role in the media assets. The method provides an objective way to quantify an actor's prominence based on billing order across multiple works.
11. A system for recommending actors based on entries in a particular database, the system comprising: control circuitry configured to: access an irrelevant actors database to determine whether the irrelevant actors database includes a promising actor, wherein the irrelevant actors database comprises a first plurality of entries, and wherein each entry of the first plurality of entries comprises an actor identifier field and an actor score field; retrieve a first threshold value, wherein the first threshold value corresponds to a minimum actor score required for including an actor in a promising actors database, wherein the promising actors database comprises a second plurality of entries, and wherein each entry of the second plurality of entries comprises the actor identifier field and the actor score field; retrieve a second threshold value, wherein the second threshold value corresponds to a minimum actor score required for including an actor in a relevant actors database; search, at a first frequency, the irrelevant actors database for an actor associated with a first entry having a value corresponding to the actor score field that is between the first threshold value and the second threshold value; retrieve, based on the searching, the first entry; update the promising actors database by including the first entry in the promising actors database; update the irrelevant actors database by deleting the first entry from the irrelevant actors database; update the actor score field corresponding to the second plurality of entries based on a pre-defined factor; search, at a second frequency, the promising actors database to determine whether the promising actors database includes a relevant actor, wherein the second frequency is greater than the first frequency; retrieve the second threshold value; determine whether the value corresponding to the actor score field associated with the first entry exceeds the second threshold value; in response to determining that the value corresponding to the actor score field associated with the first entry exceeds the second threshold value, update the relevant actors database to include the first entry; and in response to receiving a request for an actor recommendation, provide the actor recommendation based on entries in the relevant actors database.
The system recommends actors by analyzing and categorizing entries across multiple databases. It addresses the challenge of efficiently identifying and promoting suitable actors from a large pool of candidates. The system operates with three databases: an irrelevant actors database, a promising actors database, and a relevant actors database. Each database entry contains an actor identifier and an actor score. The irrelevant actors database initially holds all potential actors, while the promising and relevant databases store actors meeting specific criteria. The system first accesses the irrelevant actors database to check for actors with scores between two predefined thresholds. The lower threshold determines eligibility for the promising actors database, while the higher threshold qualifies actors for the relevant actors database. Actors meeting the lower threshold are moved from the irrelevant to the promising database, and their scores in the promising database are adjusted by a predefined factor. The promising database is then searched more frequently than the irrelevant database to assess whether any actors meet the higher threshold. If an actor's score exceeds the higher threshold, they are moved to the relevant actors database. When a request for an actor recommendation is received, the system provides suggestions based on entries in the relevant actors database. This tiered approach ensures that only the most qualified actors are recommended, improving the efficiency and accuracy of actor selection.
12. The system of claim 11 , wherein the control circuitry is further configured to: search, at the first frequency, the irrelevant actors database for a second actor associated with a second entry having a value corresponding to the actor score field exceeds the second threshold value; retrieve, based on the searching for the second actor associated with a second entry, the second entry; update the relevant actors database by including the second entry in the relevant actors database; and update the irrelevant actors database by deleting the second entry from the irrelevant actors database.
This invention relates to a system for managing and updating databases of relevant and irrelevant actors in a data processing environment. The system addresses the challenge of dynamically identifying and categorizing actors (e.g., users, entities, or processes) based on their relevance to a given context, ensuring that only pertinent actors are retained in a relevant actors database while irrelevant ones are removed. The system includes control circuitry configured to search an irrelevant actors database at a first frequency to identify a second actor associated with an entry whose actor score exceeds a second threshold value. The actor score is a metric that quantifies the relevance or importance of an actor. Upon identifying such an actor, the system retrieves the corresponding entry from the irrelevant actors database, adds it to the relevant actors database, and removes it from the irrelevant actors database. This process ensures that actors previously deemed irrelevant but now meeting the relevance criteria are reclassified and moved to the relevant database. The system operates by continuously monitoring and updating the databases to maintain accuracy and relevance, improving the efficiency of data processing tasks that rely on these databases. The dynamic adjustment of actor classifications helps in reducing noise and enhancing the performance of applications that depend on actor relevance, such as recommendation systems, fraud detection, or user behavior analysis.
13. The system of claim 11 , wherein the control circuitry is further configured to: search, at a third frequency, the relevant actors database for a third actor associated with a third entry having a value corresponding to the actor score field that is less than the second threshold value; retrieve, based on the searching for the third actor associated with a third entry, the third entry; determine whether the value corresponding to the actor score field of the third entry is less than the first threshold value; in response to determining that the value corresponding to the actor score field of the third entry is less than the first threshold value, update the irrelevant actors database by including the third entry in the irrelevant actors database; in response to determining that the value corresponding to the actor score field of the third entry is not less than the first threshold value, update the promising actors database by including the third entry in the promising actors database; and update the relevant actors database by deleting the third entry from the relevant actors database.
This invention relates to a system for managing and categorizing actors (e.g., individuals, entities, or data subjects) based on their relevance scores in a database. The system addresses the problem of efficiently identifying and classifying actors to improve data processing, decision-making, or recommendation systems by dynamically adjusting actor categorization based on their relevance scores. The system includes a relevant actors database, an irrelevant actors database, and a promising actors database. Control circuitry searches the relevant actors database at a third frequency for actors with relevance scores below a second threshold. When an actor is found, their entry is retrieved, and the system checks if their relevance score is below a first threshold. If the score is below the first threshold, the actor is moved to the irrelevant actors database. If the score is not below the first threshold, the actor is moved to the promising actors database. The actor is then removed from the relevant actors database. This process ensures that actors are dynamically reclassified based on their relevance, optimizing database organization and improving system performance. The system may also include additional databases and scoring mechanisms to further refine actor categorization.
14. The system of claim 11 , wherein the pre-defined factor based on which the actor score field associated with a given entry of the second plurality of entries is updated includes any of: a score assigned to a given actor, corresponding to the given entry, by a review source; number of media assets that the given actor has acted in; popularity of a media asset in which the given actor has acted; level of acting of the given actor; popularity of the given actor; salary of the given actor; and number of pre-defined awards that the given actor has received.
The system relates to a media asset recommendation platform that evaluates actors to improve content suggestions. The problem addressed is the lack of personalized recommendations based on actor attributes, leading to suboptimal user engagement. The system includes a database storing entries for actors, each with an actor score field that quantifies their influence or relevance. The system updates these scores based on multiple pre-defined factors, including review scores from external sources, the number of media assets an actor has appeared in, the popularity of those assets, the actor's acting level, their individual popularity, salary, and the number of awards they have received. These factors are used to dynamically adjust actor scores, which in turn influence recommendation algorithms. By incorporating diverse metrics, the system provides more accurate and tailored media recommendations to users, enhancing content discovery and user satisfaction. The approach ensures that recommendations consider both quantitative and qualitative aspects of an actor's career, improving the relevance of suggested media assets.
15. The system of claim 11 , wherein the control circuitry is further configured, when updating the actor score field corresponding to a given entry of the second plurality of entries based on the pre-defined factor, to: retrieve a first actor score assigned to a given actor, corresponding to the given entry, by a first review source; retrieve a first importance level associated with the first review source, wherein the first importance level is an indicator of how important inclusion of the first actor score is in the computation of a new actor score corresponding to the given actor; retrieve a second score assigned to the given actor by a second review source; retrieve a second importance level associated with the second review source, wherein the second importance level is an indicator of how important inclusion of the second actor score is in the computation of the new actor score corresponding to the given actor and wherein the second importance level is less than the first importance level; compute the new actor score, wherein the new actor score is a weighted average of the first actor score and the second actor score and wherein the first actor score is weighted greater than the second actor score; and update value of the actor score field corresponding to the given entry to the new actor score.
This system relates to a method for dynamically updating actor scores in a database based on weighted contributions from multiple review sources. The problem addressed is the need to accurately reflect an actor's performance or reputation by aggregating scores from different sources while accounting for the varying reliability or importance of those sources. The system includes control circuitry configured to manage a database containing entries associated with actors, where each entry includes an actor score field. When updating an actor score for a given entry, the system retrieves scores assigned to the actor by different review sources. For example, it retrieves a first score from a first review source and a second score from a second review source. Each review source has an associated importance level, which indicates how much weight its score should carry in the final calculation. The first review source is assigned a higher importance level than the second, meaning its score will have a greater influence on the updated actor score. The system computes a new actor score as a weighted average of the first and second scores, where the first score is weighted more heavily due to its higher importance level. The actor score field in the database entry is then updated with this new weighted average. This approach ensures that more reliable or authoritative review sources have a greater impact on the final score, improving the accuracy and relevance of the aggregated performance or reputation metric.
16. The system of claim 15 , wherein the first importance level is based on any of: popularity of the first review source; accuracy of the first review source; entity providing the first review source; and a user preference.
This invention relates to a system for evaluating and prioritizing review sources, addressing the challenge of determining the relevance and reliability of information from multiple review sources. The system assigns importance levels to review sources based on various factors to improve decision-making. The first importance level, which indicates the significance of a particular review source, is determined by analyzing metrics such as the popularity of the source, its accuracy, the entity providing the source, and user preferences. Popularity may be measured by the number of users engaging with the source, while accuracy could be assessed through historical verification or consistency with other sources. The entity providing the source may influence its importance, such as whether it is a trusted organization or an independent reviewer. User preferences, such as past interactions or explicit settings, can also adjust the importance level. This system helps users or automated processes filter and prioritize review sources effectively, ensuring that the most relevant and reliable information is considered. The invention enhances decision-making in applications like product reviews, news aggregation, or social media analysis by dynamically adjusting the weight of different sources based on their evaluated importance.
17. The system of claim 11 , wherein the control circuitry is further configured, when providing the actor recommendation based on entries in the relevant actors database, to: determine a user associated with the request for the actor recommendation; access a media consumption history data structure, associated with the user, to determine a first actor that the user prefers; determine a prominent role associated with the first actor, wherein the prominent role associated with the first actor is most common role of the first actor; determine a plurality of actors, included in the relevant actors database, wherein prominent role associated with each actor of the plurality of actors matches the prominent role of the first actor; and recommend a second actor of the plurality of actors.
This system operates in the domain of media content recommendation, specifically providing actor recommendations based on user preferences. The problem addressed is the challenge of suggesting relevant actors to users when they seek new content, ensuring recommendations align with their viewing habits and preferences. The system includes control circuitry that generates actor recommendations by analyzing a user's media consumption history. When a user requests an actor recommendation, the system identifies the user and accesses their media consumption history to determine a first actor they prefer. The system then identifies the most common role (prominent role) associated with this preferred actor. Using this prominent role, the system searches a relevant actors database to find other actors who have played similar prominent roles. From this filtered list, the system recommends a second actor to the user, ensuring the recommendation aligns with their established preferences. This approach enhances personalization by leveraging role-based similarities between actors, improving the likelihood that the recommended actor will appeal to the user. The system avoids generic suggestions by focusing on specific role-based patterns in the user's viewing history.
18. The system of claim 17 , wherein the control circuitry is further configured, when recommending the second actor of the plurality of actors, to: determine a prominent genre associated with the first actor, wherein the prominent genre associated with the first actor is most common genre associated with the first actor; determine an actor of the plurality of actors, wherein prominent genre associated with the actor of the plurality of actors matches the prominent genre associated with the first actor; and select the actor of the plurality of actors as the second actor.
This system relates to recommending actors in a media content creation context, addressing the challenge of identifying suitable replacements or complementary actors based on genre preferences. The system includes control circuitry configured to analyze actor data to recommend a second actor based on a first actor's prominent genre. The prominent genre is determined as the most common genre associated with the first actor's past work. The system then identifies another actor whose prominent genre matches the first actor's, ensuring compatibility in genre alignment. This actor is selected as the second actor for recommendation. The system may also involve generating a list of actors, receiving a selection of the first actor, and recommending the second actor based on the genre matching process. The recommendation process ensures that the second actor's work aligns with the genre most frequently associated with the first actor, improving relevance and coherence in actor selection for projects. This approach streamlines the casting process by leveraging genre-based matching to suggest actors with similar thematic or stylistic backgrounds.
19. The system of claim 17 , wherein the control circuitry is further configured, when recommending the second actor of the plurality of actors, to: determine a prominent media asset industry associated with the first actor, wherein the prominent media asset industry associated with the first actor is most common media asset industry associated with the first actor; determine an actor of the plurality of actors, wherein prominent media asset industry associated with the actor of the plurality of actors matches the prominent media asset industry associated with the first actor; and select the actor of the plurality of actors as the second actor.
The system is designed for recommending actors in the media industry, addressing the challenge of identifying suitable replacements or collaborators based on industry prominence. The system analyzes a first actor's career to determine their most common media asset industry, such as film, television, or theater. It then identifies other actors whose primary industry matches this dominant category. The system selects one of these actors as a second actor for recommendation, ensuring alignment with the first actor's professional focus. This approach helps in casting decisions, collaborative projects, or market analysis by leveraging industry-specific expertise. The system may also consider additional factors, such as performance metrics or historical data, to refine recommendations. The core functionality involves automated industry classification and matching, reducing manual effort and improving accuracy in actor selection. This method is particularly useful in entertainment production, talent agencies, and content development, where industry relevance is critical.
20. The system of claim 17 , wherein the control circuitry is configured, when determining the prominent role associated with the first actor, to: determine a first media asset in which the first actor appears; retrieve a first credit list associated with the first media asset, wherein the first credit lists all actors appearing in the first media asset; determine a first position of the first actor in the first credit list and a total number of actors in the first credit list; compute a first rank percentage of the first actor based on the first position of the first actor in the first credit list and the total number of actors in the first credit list; determine a second media asset in which the first actor appears; retrieve a second credit list associated with the second media asset, wherein the second credit lists all actors appearing in the second media asset; determine a second position of the first actor in the second credit list and a total number of actors in the second credit list; compute a second rank percentage of the first actor based on the second position of the first actor in the second credit list and the total number of actors in the second credit list; compute, based on the first rank percentage and the second rank percentage, an average rank percentage of the first actor; retrieve a role probability distribution wherein the role probability distribution provides probabilities of various roles in media assets; determine a first role associated with the role probability distribution that has a cumulative probability range that includes the average rank percentage of the first actor; and select the first role as the prominent role.
The system determines the prominence of an actor in media assets by analyzing their credit list rankings. For a given actor, the system identifies multiple media assets in which they appear and retrieves the credit lists for each asset, which include all actors involved. The system then calculates the actor's position in each credit list and computes a rank percentage based on their position relative to the total number of actors. These rank percentages are averaged across all media assets. The system then uses a role probability distribution, which maps rank percentages to specific roles (e.g., lead, supporting, minor), to determine the actor's most likely role. The role with a cumulative probability range that includes the actor's average rank percentage is selected as their prominent role. This method quantifies an actor's prominence by leveraging credit list data and statistical distributions, providing a data-driven approach to role classification in media assets.
Unknown
March 17, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.